Presentation | 2003/9/9 Information Clipping from Internet Documents with Similar Contexts Eiji MURAKAMI, Takao TERANO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | There are so many documents available in the Internet. Some of them implicitly share common contexts. The examples of contexts covers pre-determined tasks, i.e., sales reports, categories, i.e., concept hierarchies, and forums, i.e., special interest groups. By clipping, we mean (1) to define the importance measures of documents in the same context, and (2) to acquire the important statement(s) from the documents based on the measure. This paper describes a new method of information clipping suitable for the group of documents gathered from a certain context retrieved in the Internet. The basic steps of the method is (1) to get key words using KeyGraph from a given set of documents, (2) to cluster the documents by applying Dulmage Mendelsohn decomposition algorithm for bipartite graphs, which consist of the nodes of the important words and the documents and the edges to represent their inclusion relationship, and (3) to acquire the corresponding important sentences. The paper shows some experimental results to reveal the effectiveness of the proposed method using a prototype system applied to the practical internet documents. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Information clipping / clustering / summarization |
Paper # | AI2003-60 |
Date of Issue |
Conference Information | |
Committee | AI |
---|---|
Conference Date | 2003/9/9(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Artificial Intelligence and Knowledge-Based Processing (AI) |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Information Clipping from Internet Documents with Similar Contexts |
Sub Title (in English) | |
Keyword(1) | Information clipping |
Keyword(2) | clustering |
Keyword(3) | summarization |
1st Author's Name | Eiji MURAKAMI |
1st Author's Affiliation | Graduate School of Business Sciences, University of Tsukuba() |
2nd Author's Name | Takao TERANO |
2nd Author's Affiliation | Graduate School of Business Sciences, University of Tsukuba |
Date | 2003/9/9 |
Paper # | AI2003-60 |
Volume (vol) | vol.103 |
Number (no) | 306 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |